Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Medical advice and warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terrorists
    -0.07
    abstract
    -0.07
    矩
    -0.07
     Terror
    -0.07
    alesce
    -0.07
     explanatory
    -0.07
    ales
    -0.07
    战略
    -0.07
    Winning
    -0.07
     pixel
    -0.07
    POSITIVE LOGITS
     противопоказ
    0.17
     contraind
    0.15
     dosing
    0.14
     सेवन
    0.13
     doses
    0.13
     placebo
    0.12
     peppermint
    0.12
     precaution
    0.12
     аллерг
    0.12
     dosage
    0.12
    Act Density 0.021%

    No Known Activations